Circleci
Use when the user asks about CircleCI, .circleci/config.yml, orbs, executors, workflows, contexts, save_cache/restore_cache, test splitting, parallelism, self-hosted runners, or SSH debug. Produces CircleCI configs. Not for GitHub Actions (use github-actions) or GitLab CI (use devops-gitlab-ci).
Install
npx skills add j4flmao/agent-skills --skill circlecigit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/devops/circleci ~/.claude/skills/circleciPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# CircleCI
## Purpose
Define CI/CD pipelines using CircleCI configuration with workflows, jobs, orbs, caching strategies, and parallel execution for fast, reliable builds.
## Agent Protocol
### Trigger
"CircleCI", "circleci config", "orb", "executors", "CircleCI runner", "test splitting", "dynamic config".
### Input Context
Languages, test suite duration, executor needs (Docker, machine, macOS, Arm), contexts/secrets, monorepo layout.
### Output Artifact
`.circleci/config.yml` and orb usage. No file unless requested.
### Response Format
```
Executor: {docker|machine|macos|windows|self-hosted runner}
Workflow: {jobs and dependencies}
Caching: {cache key template}
Parallelism: {test splitting by timings}
Config: {.circleci/config.yml snippet}
```
## Architecture Decision Trees
### Executor Selection
| Executor | Speed | Best For | Limitations |
|---|---|---|---|
| Docker | Fast (<30s start) | Standard builds | Container-only, limited to Docker |
| Machine | Slow (~60s start) | Docker-in-Docker, full VM | More expensive, fewer concurrent jobs |
| macOS | Slow | iOS/macOS builds | Apple-only, limited parallelism |
| Windows | Moderate | .NET, Windows-specific | Limited images, slower startup |
| GPU (Linux) | Fast | ML/DL training | Expensive, limited availability |
### Caching Strategy
| Strategy | Save Key | Restore Keys | Use Case |
|---|---|---|---|
| Lockfile hash | `v1-deps-{{ checksum "package-lock.json" }}` | `v1-deps-` | Node.js, Go, Rust |Details
- Skill name
circleci- Repository
- j4flmao/agent-skills
- Path
skills/devops/circleci/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Circleci skill do?
Use when the user asks about CircleCI, .circleci/config.yml, orbs, executors, workflows, contexts, save_cache/restore_cache, test splitting, parallelism, self-hosted runners, or SSH debug. Produces CircleCI configs. Not for GitHub Actions (use github-actions) or GitLab CI (use devops-gitlab-ci).
How do I install the Circleci skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill circleci. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Circleci popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Cloud Migration
45j4flmao/agent-skills
Use when the user asks about cloud migration, lift and shift, the 7 Rs (rehost, replatform, refactor), AWS MGN, Azure Migrate, migration waves, discovery and assessment, or cutover planning. Produces a migration plan with waves, tooling and rollback. Not for database schema migrations (use database-migration) or hybrid connectivity (use hybrid-cloud).
Cilium Ebpf
45j4flmao/agent-skills
Use when the user asks about installing Cilium CNI, Hubble, CiliumNetworkPolicy, Cluster Mesh, Cilium kube-proxy replacement, WireGuard or IPsec encryption, Cilium Gateway API, or Tetragon. Produces Cilium Helm values, policies and operational checks. Not for eBPF datapath internals (use cloud-native-ebpf-networking) or Istio/Linkerd (use devops-service-mesh).
Cloud Native AWS Serverless
45j4flmao/agent-skills
Use when the user asks about AWS Lambda internals, Firecracker microVMs, the execution environment lifecycle, concurrency limits, event source mappings, function URLs, layers, or Lambda timeouts. Produces correct Lambda function design and configuration. Not for cold-start tuning (use cloud-native-serverless-cold-starts) or Step Functions (use cloud-native-serverless-orchestration).
Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.